TY - GEN
T1 - Detecting Adversarial Images via Texture Analysis
AU - Chai, Weiheng
AU - Velipasalar, Senem
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/11/1
Y1 - 2020/11/1
N2 - Neural networks have been shown to be vulnerable to carefully crafted adversarial examples. Recently, new adversarial attacks, including dispersion reduction (DR), have been proposed, and shown to be transferable across different computer vision tasks. This means that an ensemble of different defense/detection mechanisms can be evaded all at once. Unlike previous attack methods, the DR attack minimizes the dispersion of an internal feature map providing state-of-the-art results. In this paper, we propose an algorithm to detect the adversarial examples generated by different adversarial attacks, including the dispersion reduction, projected gradient descent, diverse inputs method and momentum iterative fast gradient sign method. Our approach employs 1D Gabor filter responses, and detects adversarial examples generated from different surrogate neural network models and datasets with high accuracy.
AB - Neural networks have been shown to be vulnerable to carefully crafted adversarial examples. Recently, new adversarial attacks, including dispersion reduction (DR), have been proposed, and shown to be transferable across different computer vision tasks. This means that an ensemble of different defense/detection mechanisms can be evaded all at once. Unlike previous attack methods, the DR attack minimizes the dispersion of an internal feature map providing state-of-the-art results. In this paper, we propose an algorithm to detect the adversarial examples generated by different adversarial attacks, including the dispersion reduction, projected gradient descent, diverse inputs method and momentum iterative fast gradient sign method. Our approach employs 1D Gabor filter responses, and detects adversarial examples generated from different surrogate neural network models and datasets with high accuracy.
UR - http://www.scopus.com/inward/record.url?scp=85107783124&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85107783124&partnerID=8YFLogxK
U2 - 10.1109/IEEECONF51394.2020.9443449
DO - 10.1109/IEEECONF51394.2020.9443449
M3 - Conference contribution
AN - SCOPUS:85107783124
T3 - Conference Record - Asilomar Conference on Signals, Systems and Computers
SP - 215
EP - 219
BT - Conference Record of the 54th Asilomar Conference on Signals, Systems and Computers, ACSSC 2020
A2 - Matthews, Michael B.
PB - IEEE Computer Society
T2 - 54th Asilomar Conference on Signals, Systems and Computers, ACSSC 2020
Y2 - 1 November 2020 through 5 November 2020
ER -